cahya commited on
Commit
18cd1c6
1 Parent(s): dbaca8d

updated the model

Browse files
config.json CHANGED
@@ -1,14 +1,11 @@
1
  {
2
- "_name_or_path": "indonesian-nlp/wav2vec2-luganda",
3
- "activation_dropout": 0.1,
4
- "adapter_kernel_size": 3,
5
- "adapter_stride": 2,
6
- "add_adapter": false,
7
  "apply_spec_augment": true,
8
  "architectures": [
9
  "Wav2Vec2ForCTC"
10
  ],
11
- "attention_dropout": 0.0,
12
  "bos_token_id": 1,
13
  "classifier_proj_size": 256,
14
  "codevector_dim": 768,
@@ -49,32 +46,30 @@
49
  "feat_extract_activation": "gelu",
50
  "feat_extract_dropout": 0.0,
51
  "feat_extract_norm": "layer",
52
- "feat_proj_dropout": 0.0,
53
  "feat_quantizer_dropout": 0.0,
54
  "final_dropout": 0.0,
 
55
  "hidden_act": "gelu",
56
- "hidden_dropout": 0.0,
57
  "hidden_size": 1024,
58
  "initializer_range": 0.02,
59
  "intermediate_size": 4096,
60
  "layer_norm_eps": 1e-05,
61
- "layerdrop": 0.0,
62
  "mask_channel_length": 10,
63
  "mask_channel_min_space": 1,
64
  "mask_channel_other": 0.0,
65
  "mask_channel_prob": 0.0,
66
  "mask_channel_selection": "static",
67
- "mask_feature_length": 64,
68
- "mask_feature_min_masks": 0,
69
- "mask_feature_prob": 0.25,
70
  "mask_time_length": 10,
71
- "mask_time_min_masks": 2,
72
  "mask_time_min_space": 1,
73
  "mask_time_other": 0.0,
74
  "mask_time_prob": 0.4,
75
  "mask_time_selection": "static",
76
  "model_type": "wav2vec2",
77
- "num_adapter_layers": 3,
78
  "num_attention_heads": 16,
79
  "num_codevector_groups": 2,
80
  "num_codevectors_per_group": 320,
@@ -83,33 +78,10 @@
83
  "num_feat_extract_layers": 7,
84
  "num_hidden_layers": 24,
85
  "num_negatives": 100,
86
- "output_hidden_size": 1024,
87
  "pad_token_id": 28,
88
  "proj_codevector_dim": 768,
89
- "tdnn_dilation": [
90
- 1,
91
- 2,
92
- 3,
93
- 1,
94
- 1
95
- ],
96
- "tdnn_dim": [
97
- 512,
98
- 512,
99
- 512,
100
- 512,
101
- 1500
102
- ],
103
- "tdnn_kernel": [
104
- 5,
105
- 3,
106
- 3,
107
- 1,
108
- 1
109
- ],
110
  "torch_dtype": "float32",
111
- "transformers_version": "4.17.0.dev0",
112
  "use_weighted_layer_sum": false,
113
- "vocab_size": 29,
114
- "xvector_output_dim": 512
115
  }
 
1
  {
2
+ "_name_or_path": "/workspace/output_models/wav2vec2-common_voice-lg-tvoi-2",
3
+ "activation_dropout": 0.055,
 
 
 
4
  "apply_spec_augment": true,
5
  "architectures": [
6
  "Wav2Vec2ForCTC"
7
  ],
8
+ "attention_dropout": 0.094,
9
  "bos_token_id": 1,
10
  "classifier_proj_size": 256,
11
  "codevector_dim": 768,
 
46
  "feat_extract_activation": "gelu",
47
  "feat_extract_dropout": 0.0,
48
  "feat_extract_norm": "layer",
49
+ "feat_proj_dropout": 0.04,
50
  "feat_quantizer_dropout": 0.0,
51
  "final_dropout": 0.0,
52
+ "gradient_checkpointing": false,
53
  "hidden_act": "gelu",
54
+ "hidden_dropout": 0.047,
55
  "hidden_size": 1024,
56
  "initializer_range": 0.02,
57
  "intermediate_size": 4096,
58
  "layer_norm_eps": 1e-05,
59
+ "layerdrop": 0.041,
60
  "mask_channel_length": 10,
61
  "mask_channel_min_space": 1,
62
  "mask_channel_other": 0.0,
63
  "mask_channel_prob": 0.0,
64
  "mask_channel_selection": "static",
65
+ "mask_feature_length": 10,
66
+ "mask_feature_prob": 0.0,
 
67
  "mask_time_length": 10,
 
68
  "mask_time_min_space": 1,
69
  "mask_time_other": 0.0,
70
  "mask_time_prob": 0.4,
71
  "mask_time_selection": "static",
72
  "model_type": "wav2vec2",
 
73
  "num_attention_heads": 16,
74
  "num_codevector_groups": 2,
75
  "num_codevectors_per_group": 320,
 
78
  "num_feat_extract_layers": 7,
79
  "num_hidden_layers": 24,
80
  "num_negatives": 100,
 
81
  "pad_token_id": 28,
82
  "proj_codevector_dim": 768,
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
83
  "torch_dtype": "float32",
84
+ "transformers_version": "4.11.2",
85
  "use_weighted_layer_sum": false,
86
+ "vocab_size": 29
 
87
  }
pytorch_model.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:0aff8a4703a7e6506993a449bf58551b3300d38e6a314c673a6e745d0b5c48d8
3
  size 1262042545
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:447bf4c640af086f70af1eaeca3850c694f9d56aa085922fd02839673b611805
3
  size 1262042545
special_tokens_map.json CHANGED
@@ -1 +1 @@
1
- {"unk_token": "[UNK]", "pad_token": "[PAD]"}
 
1
+ {"bos_token": "<s>", "eos_token": "</s>", "unk_token": "[UNK]", "pad_token": "[PAD]"}
tokenizer_config.json CHANGED
@@ -1 +1 @@
1
- {"unk_token": "[UNK]", "bos_token": null, "eos_token": null, "pad_token": "[PAD]", "do_lower_case": false, "word_delimiter_token": "|", "special_tokens_map_file": null, "tokenizer_file": null, "name_or_path": "./", "tokenizer_class": "Wav2Vec2CTCTokenizer"}
 
1
+ {"unk_token": "[UNK]", "bos_token": "<s>", "eos_token": "</s>", "pad_token": "[PAD]", "do_lower_case": false, "word_delimiter_token": "|", "tokenizer_class": "Wav2Vec2CTCTokenizer"}
vocab.json CHANGED
@@ -1 +1 @@
1
- {"-": 1, "a": 2, "b": 3, "c": 4, "d": 5, "e": 6, "f": 7, "g": 8, "h": 9, "i": 10, "j": 11, "k": 12, "l": 13, "m": 14, "n": 15, "o": 16, "p": 17, "r": 18, "s": 19, "t": 20, "u": 21, "v": 22, "w": 23, "x": 24, "y": 25, "z": 26, "|": 0, "[UNK]": 27, "[PAD]": 28}
 
1
+ {"a": 1, "b": 2, "c": 3, "d": 4, "e": 5, "f": 6, "g": 7, "h": 8, "i": 9, "j": 10, "k": 11, "l": 12, "m": 13, "n": 14, "o": 15, "p": 16, "q": 17, "r": 18, "s": 19, "t": 20, "u": 21, "v": 22, "w": 23, "x": 24, "y": 25, "z": 26, "|": 0, "[UNK]": 27, "[PAD]": 28}